sketch2symm: Symmetry-aware sketch-to-shape generation via semantic bridging

📅 2025-10-13
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
Sketch-based 3D reconstruction faces significant challenges due to the abstract, sparse nature of input sketches and their limited semantic and geometric information. To address this, we propose a two-stage generative framework that jointly leverages semantic bridging and symmetry constraints. First, a sketch-to-image translation module establishes cross-modal semantic alignment, mitigating information scarcity. Second, a symmetry-aware 3D reconstruction network incorporates reflection symmetry as a strong geometric prior to enhance structural plausibility and completeness. Evaluated on mainstream sketch datasets including ShapeNet, our method achieves state-of-the-art performance across all three core metrics—Chamfer Distance, Earth Mover’s Distance, and F-Score—demonstrating the effectiveness of co-modeling semantic guidance and geometric priors for sketch-based 3D reconstruction.

Technology Category

Application Category

📝 Abstract
Sketch-based 3D reconstruction remains a challenging task due to the abstract and sparse nature of sketch inputs, which often lack sufficient semantic and geometric information. To address this, we propose Sketch2Symm, a two-stage generation method that produces geometrically consistent 3D shapes from sketches. Our approach introduces semantic bridging via sketch-to-image translation to enrich sparse sketch representations, and incorporates symmetry constraints as geometric priors to leverage the structural regularity commonly found in everyday objects. Experiments on mainstream sketch datasets demonstrate that our method achieves superior performance compared to existing sketch-based reconstruction methods in terms of Chamfer Distance, Earth Mover's Distance, and F-Score, verifying the effectiveness of the proposed semantic bridging and symmetry-aware design.
Problem

Research questions and friction points this paper is trying to address.

Generating 3D shapes from sparse, abstract sketches
Enriching sketch inputs via semantic image translation
Incorporating symmetry constraints as geometric priors
Innovation

Methods, ideas, or system contributions that make the work stand out.

Two-stage generation for sketch-to-shape conversion
Semantic bridging via sketch-to-image translation
Symmetry constraints as geometric priors
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
Y
Yan Zhou
School of Electronic Information Engineering, Foshan University, Guangdong, China
M
Mingji Li
School of Computer Science and Artificial Intelligence, Foshan University, Guangdong, China
X
Xiantao Zeng
School of Computer Science and Artificial Intelligence, Foshan University, Guangdong, China
J
Jie Lin
School of Electronic Information Engineering, Foshan University, Guangdong, China
Y
Yuexia Zhou
School of Electronic Information Engineering, Foshan University, Guangdong, China